Human-Centered Approaches to Designing Intelligent Agents' Manner for Supporting High-Level Thinking

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


PhD Thesis Defence


Title: "Human-Centered Approaches to Designing Intelligent Agents' Manner for 
Supporting High-Level Thinking"

By

Mr. Zhenhui PENG


Abstract

High-level thinking, such as decision-making, problem solving, and critical 
thinking, is an essential skill that people need to learn and apply in their 
daily lives. Such thinking is often complex, and people can traditionally get 
help from others for task completion. For example, students can get guidance 
from instructors on how to read papers critically. However, such human experts 
are not always available. Intelligent agents in a robot or bot form can 
mitigate this issue by socially offering real-time assistance to users. Yet, it 
is challenging to design the agents that can appropriately support users in 
high-level thinking tasks, because interacting with the agents may distract 
users from the main tasks which could require a lot of mental effort. 
Researchers of these intelligent agents need to answer: where can the agents 
offer help; how to design their behaviors; how to develop the agents for design 
validation; and how to evaluate the proposed design.

My thesis research investigates the design and user experience of intelligent 
agents and their manner (i.e., way of behaving) for supporting users’ 
high-level thinking tasks. To address the design questions mentioned above, I 
adopt a set of human-centered approaches that first discover the usage 
scenarios of the agents by emphasizing with targeted users. Then I design the 
agents and their manners by summarizing human assistants’ behavioral patterns 
and existing technological practices. Next, I develop the agent prototypes and 
evaluate our design via user studies with targeted users. I adopt this approach 
to design and evaluate intelligent agents in three high-level thinking support 
contexts separately, i.e., decision-making, problem solving, and critical 
thinking.

In the first study, we learn from human workers’ behaviors and robot’s autonomy 
to model the service robot’s proactivity (low, medium, high) in decision-making 
support tasks. Our experiment in a simulated shopping scenario shows that a 
highly proactive robot is deemed inappropriate, the one with medium proactivity 
helps reduce the decision space, and the least proactive robot grants users 
more control but may not realize its full capability.

The second study explores a problem-solving scenario where we propose a writing 
assistant MepsBot for peers to compose solutions to help seekers’ problems in 
online mental health communities. Inspired by design practices of existing 
writing support tools, we develop MepsBot with two assistant mechanisms, i.e., 
AS mode that assesses writing performance and RE mode that recommends similar 
high-quality examples. Our lab experiment found that AS-mode MepsBot encourages 
users to refine expressions and is deemed easier to use, while the RE-mode one 
stimulates more support-related content re-editions.

In the third study, we target students’ needs of critical thinking during their 
academic paper reading process. Learned from the paper reading experience of 
senior researchers and the design practice of chatbots, we propose a CReBot 
that asks questions to encourage critical thinking when users read each paper 
section. In comparison to the guidelines that list all questions, our 
experiment indicates that CReBot encourages more critical reading behaviors and 
significantly improves users’ perceived performance in paper reinterpretation.

In all, my three works demonstrate the feasibility of the proposed 
human-centered approaches to designing appropriate and useful intelligent 
agents for supporting high-level thinking. We conclude the thesis proposal with 
future work for generalizing our methods and proposed intelligent agents.


Date:			Friday, 12 March 2021

Time:			3:00pm - 5:00pm

Zoom Meeting: 
https://hkust.zoom.us/j/95053480747?pwd=SWtXMUx5QUJ2UTRzbU1taC8xUlhQdz09


Chairperson:		Prof. Jianfeng CAI (MATH)

Committee Members:	Prof. Xiaojuan MA (Supervisor)
 			Prof. Qiong LUO
 			Prof. Chiew Lan TAI
 			Prof. Dongwon LEE (ISOM)
 			Prof. Juho KIM (KAIST)


**** ALL are Welcome ****